Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
We present a syntactically enriched vector model that supports the computation of contextualized semantic representations in a quasi compositional fashion. It employs a systematic combination of first- and second-order context vectors. We apply our model to two different tasks and show that (i) it substantially outperforms previous work on a paraphrase ranking task, and (ii) achieves promising results on a wordsense similarity task; to our knowledge, it is the first time that an unsupervised method has been applied to this task. . | Contextualizing Semantic Representations Using Syntactically Enriched Vector Models Stefan Thater and Hagen Furstenau and Manfred Pinkal Department of Computational Linguistics Saarland University stth hagenf pinkal @coli.uni-saarland.de Abstract We present a syntactically enriched vector model that supports the computation of contextualized semantic representations in a quasi compositional fashion. It employs a systematic combination of first- and second-order context vectors. We apply our model to two different tasks and show that i it substantially outperforms previous work on a paraphrase ranking task and ii achieves promising results on a wordsense similarity task to our knowledge it is the first time that an unsupervised method has been applied to this task. 1 Introduction In the logical paradigm of natural-language semantics originating from Montague 1973 semantic structure composition and entailment have been modelled to an impressive degree of detail and formal consistency. These approaches however lack coverage and robustness and their impact on realistic natural-language applications is limited The logical framework suffers from overspecificity and is inappropriate to model the pervasive vagueness ambivalence and uncertainty of natural-language semantics. Also the handcrafting of resources covering the huge amounts of content which are required for deep semantic processing is highly inefficient and expensive. Co-occurrence-based semantic vector models offer an attractive alternative. In the standard approach word meaning is represented by feature vectors with large sets of context words as dimensions and their co-occurrence frequencies as values. Semantic similarity information can be acquired using unsupervised methods at virtually no cost and the information gained is soft and gradual. Many NLP tasks have been modelled successfully using vector-based models. Examples include in formation retrieval Manning et al. 2008 wordsense discrimination Schutze .
